Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference

arXiv:2611.01320 · cs.CL, cs.AI · Submitted 2026-10-31 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-31

Updated: 2026-10-31

Terminology

Sources

Related papers